Skip to content

An image restoration framework (Image Deraining code has been implemented) based on the Restormer model as a back-bone. This is an early idea in my "Attending to the past" research project. This model with roughly the same amount of learnable parameters shows better performance under the same training methods

License

MohsenAmiri79/PASTormer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is the PASTormer V1 model

Getting Started

To use your own data with this project, follow these steps:

  1. Clone the Repository: Clone this repository to your local machine.

    git clone https://github.com/MohsenAmiri79/PASTormer.git
  2. Navigate to the "data" directory: Use the command line to navigate to the "data" directory within the cloned repository.

    cd your-repo/data
  3. Organize Your Data:

    • Training Data:

      • Place your training images in the "training/x" directory.
      • Place the corresponding ground truth images in the "training/y" directory.
    • Validation Data:

      • Place your validation/query images in the "validation/x" directory.
      • Place the corresponding ground truth images in the "validation/y" directory.
  4. Use the Project: You can now use the project with your own data by following the project's instructions.

Project Dependencies

einops==0.6.1 matplotlib==3.7.3 numpy==1.25.2 Pillow==10.0.0 pytorch-msssim==1.0.0 torch==2.0.1 torchvision==0.15.2

License

This project is licensed under the MIT License. See the LICENSE FILE for details.

About

An image restoration framework (Image Deraining code has been implemented) based on the Restormer model as a back-bone. This is an early idea in my "Attending to the past" research project. This model with roughly the same amount of learnable parameters shows better performance under the same training methods

Topics

Resources

License

Stars

Watchers

Forks